refactor(mcp): make MCP test reuse the shared Box session (near-instant tests) (#2304)

* refactor(mcp): make MCP test reuse the shared Box session instead of a per-test session

Testing an MCP server (config-page "test" button) previously spun up a fresh
isolated mcp-test-<uuid> Box session every time: cold-start the container, run
the dependency bootstrap, probe, then tear the whole session down. That is slow
(tens of seconds) and, on an already-hosted server, wasteful — the server is
already running in the shared session.

Change the test to reuse the shared session / live process:

- _build_box_session_id: transient tests now use mcp-shared, the same Box
  session as live servers, so a test reuses the running container (and, for an
  existing server, its live managed process) instead of a cold per-test session.
- cleanup_session: a transient test no longer deletes the whole session (which
  under the shared model would kill every other MCP server in the container). It
  stops only its own process_id, exactly like a live server. Isolation is now at
  the process level (distinct process_id per server/test), not the session level.
- test_mcp_server (persisted server): reuse the live connection with a real
  list_tools refresh/probe; only fall back to a full start() when there is no
  live connection to probe or the refresh fails, instead of an ERROR->start()
  rebuild.

Trade-off: a failing test now shares the container with live servers rather than
a throwaway session. Accepted deliberately in favour of near-instant tests;
process-level isolation keeps a test from stopping another server's process.

* chore(deps): pin langbot-plugin 0.4.9 for the nsjail RLIMIT_AS node/npx MCP fix

---------

Co-authored-by: dadachann <185672915+dadachann@users.noreply.github.com>

src/langbot/pkg/provider/tools/loaders/mcp.py

@@ -986,11 +986,14 @@ class RuntimeMCPSession:
         return self._box_stdio_runtime.uses_box_stdio()
 
     def _build_box_session_id(self) -> str:
-        # Transient test sessions get their own isolated Box session so a
-        # failing/short-lived test can never disturb the shared session that
-        # hosts live, already-connected MCP servers.
-        if self.is_transient:
-            return f'mcp-test-{self.server_uuid}'
+        # Both live servers and transient config-page tests share ONE Box
+        # session ('mcp-shared'). A test therefore reuses the already-running
+        # container (and, for an existing server, its live managed process)
+        # instead of paying a full per-test session cold-start + dependency
+        # bootstrap. Isolation between a test and the live servers is provided
+        # at the *process* level: each server/test has its own process_id and a
+        # test only ever stops its own process_id (see cleanup_session), so it
+        # never disturbs another server's process or the shared session itself.
         return 'mcp-shared'
 
     def _rewrite_path(self, path: str, host_path: str | None) -> str: